AI Paper Atlas

Research map / Video / Video-language understanding

Text-Conditioned Resampler For Long Form Video Understanding

Bruno Korbar, Yongqin Xian, Alessio Tonioni, Andrew Zisserman, Federico Tombari

ECCV 2024 · Video › Video-language understanding · approach: Video LLMs with fine-grained understanding · 14 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add task-conditioning text to the resampler (ablation)TCR · NextQA temporal questionsaccuracy: 61.1 -> 64.9Improved
corrupt the temporal word in conditioning (before/after swap) (ablation)TCR · NextQA temporal questionsaccuracy: 64.9 -> 55.3Hurt
add initialisation stage (contrastive and matching) (ablation)TCR · NextQA val (short schedule)accuracy: 63.3 -> 66.1Improved
add pre-training with LLM on YTT-1B (ablation)TCR · NextQA val (short schedule)accuracy: 52.1 -> 66.1Improved
add denoising pre-training task (iii) (ablation)TCR pre-training · NextQA val (short schedule)accuracy: 65.6 -> 66.1Improved
increase input frames from 32 to 92 (ablation)TCR · NextQA val (short schedule)accuracy: 64.4 -> 66.2Improved
increase input frames from 92 to 124 (ablation)TCR · NextQA val (short schedule)accuracy: 66.2 -> 65.9No clear effect
use 128 queries instead of 32 or 256 (ablation)TCR · NextQA val (short schedule)accuracy: 62.7 / 64.3 -> 66.2Mixed
add task-specific special tokens (ablation)TCR · NextQA valaccuracy: 72.7 -> 73.5Improved
increase observed frames from 8 to 92 with TCR (vs BLIP2 averaging)BLIP2 · EgoSchemaQA accuracy (%): 27.2 -> 34.2Improved
observe the whole video instead of only before the last action (ablation)TCR · Ego4D LTA valActionED: 0.8792 -> 0.8522Improved
TCR generative LLM approach vs ASL specialist on moment queriesTCR · Ego4D Moment Queries valavg mAP: 27.85 -> 25.45Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 2 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy